CN113450168A - Data processing method, device and computer readable storage medium - Google Patents
Data processing method, device and computer readable storage medium Download PDFInfo
- Publication number
- CN113450168A CN113450168A CN202010228286.4A CN202010228286A CN113450168A CN 113450168 A CN113450168 A CN 113450168A CN 202010228286 A CN202010228286 A CN 202010228286A CN 113450168 A CN113450168 A CN 113450168A
- Authority
- CN
- China
- Prior art keywords
- commodity
- link
- resource configuration
- configuration data
- historical
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000003672 processing method Methods 0.000 title claims abstract description 25
- 238000006243 chemical reaction Methods 0.000 claims abstract description 159
- 238000012545 processing Methods 0.000 claims abstract description 20
- 238000000034 method Methods 0.000 claims abstract description 11
- 230000002596 correlated effect Effects 0.000 claims description 11
- 238000013507 mapping Methods 0.000 claims description 11
- 238000010586 diagram Methods 0.000 description 18
- 238000013468 resource allocation Methods 0.000 description 14
- 238000004590 computer program Methods 0.000 description 5
- 238000004364 calculation method Methods 0.000 description 4
- 230000000875 corresponding effect Effects 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 230000000694 effects Effects 0.000 description 3
- 238000004422 calculation algorithm Methods 0.000 description 2
- 230000003044 adaptive effect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000006855 networking Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0631—Item recommendations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/958—Organisation or management of web site content, e.g. publishing, maintaining pages or automatic linking
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0633—Lists, e.g. purchase orders, compilation or processing
- G06Q30/0635—Processing of requisition or of purchase orders
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- General Physics & Mathematics (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Physics & Mathematics (AREA)
- Economics (AREA)
- General Business, Economics & Management (AREA)
- Strategic Management (AREA)
- Marketing (AREA)
- Development Economics (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The disclosure provides a data processing method, a data processing device and a computer readable storage medium, and relates to the technical field of computers. The data processing method comprises the following steps: generating resource configuration data of the commodity link according to the historical click times and the historical order conversion rate of the commodity link; the resource configuration data is in negative correlation with the historical click times, and the resource configuration data is in positive correlation with the historical order conversion rate; and inputting the commodity identification and the resource configuration data of the commodity link into the link publishing engine so that the link publishing engine publishes the commodity link according to the commodity identification and the resource configuration data of the commodity link. According to the method and the device, the resource configuration data input to the link publishing engine can be determined for a single commodity link according to the historical click times and the historical order conversion rate of the commodity link, so that the order conversion rate of the commodity link is improved, and the publishing efficiency of the commodity link is improved.
Description
Technical Field
The present disclosure relates to the field of computer technologies, and in particular, to a data processing method and apparatus, and a computer-readable storage medium.
Background
The e-commerce platform typically needs to publish the merchandise links through a link publication engine.
Before the commodity link is released, the e-commerce platform needs to divide commodities of the same category into a commodity group, and input the uniform resource configuration data and the commodity group number of the commodity group into the link release engine. The link publishing engine selects commodity links of part of commodities from each commodity group according to each commodity group number and corresponding resource configuration data and publishes the commodity links to the user.
Disclosure of Invention
The technical problem solved by the present disclosure is how to improve the release efficiency of the commodity link.
According to an aspect of the embodiments of the present disclosure, there is provided a data processing method, including: generating resource configuration data of the commodity link according to the historical click times and the historical order conversion rate of the commodity link; the resource configuration data is in negative correlation with the historical click times, and the resource configuration data is in positive correlation with the historical order conversion rate; and inputting the commodity identification and the resource configuration data of the commodity link into the link publishing engine so that the link publishing engine publishes the commodity link according to the commodity identification and the resource configuration data of the commodity link.
In some embodiments, generating the resource configuration data of the commodity link according to the historical click times and the historical order conversion rate of the commodity link includes: generating a resource configuration data reference value of the commodity link according to the historical click times and the historical order conversion rate of the commodity link; determining a value interval of the resource configuration data of the commodity link according to the historical click times and the historical order conversion rate of the commodity link; and mapping the reference value of the resource configuration data to a value interval to obtain the resource configuration data.
In some embodiments, determining the value section of the resource configuration data of the commodity link according to the historical click times and the historical order conversion rate of the commodity link includes: under the condition that the historical click times are larger than a first threshold value and the historical order conversion rate is larger than a second threshold value, the value-taking interval is [ F ]1,F2](ii) a CalendarUnder the condition that the history click times are not more than a first threshold value and the history order conversion rate is more than a second threshold value, the value-taking interval is [ F1,F3](ii) a Under the condition that the historical click times are larger than a first threshold value and the historical order conversion rate is not larger than a second threshold value, the value-taking interval is [ F ]3,F5](ii) a Under the condition that the historical click times are larger than a first threshold value and the historical order conversion rate is not larger than a second threshold value, the value-taking interval is [ F ]4,F5](ii) a Wherein, F1>F2>F3>F4>F5>0。
In some embodiments, generating the resource configuration data reference value of the commodity link according to the historical click times and the historical order conversion rate of the commodity link includes: generating a target component of a resource configuration data reference value according to the historical click times and the historical order conversion rate of the commodity link in the target link publishing engine; generating a global component of a resource configuration data reference value according to historical click times and historical order conversion rates of commodity links in all link publishing engines; determining a resource configuration data reference value of the commodity link in the target link publishing engine according to the sum of the target component and the global component; determining the value interval of the resource configuration data of the commodity link according to the historical click times and the historical order conversion rate of the commodity link comprises the following steps: determining a value interval of resource configuration data of the commodity link according to the historical click times and the historical order conversion rate of the commodity link in the target link publishing engine; mapping the reference value of the resource configuration data to a value interval, and acquiring the resource configuration data comprises the following steps: mapping the resource configuration data reference value of the commodity link in the target link publishing engine to a value range to obtain the resource configuration data of the commodity link in the target link publishing engine; the method for inputting the commodity identification and the resource configuration data of the commodity link into the link publishing engine comprises the following steps: and inputting the commodity identification and the resource configuration data of the commodity link in the target link publishing engine into the target link publishing engine.
In some embodiments, determining the resource configuration data reference value of the commodity link in the target link publishing engine according to the sum of the target component and the global component comprises: adding the target component, the global component and the session component to obtain a resource configuration data reference value of the commodity link in a target link publishing engine; the session components are: and the number of sessions that the commodity is added into a shopping cart or placed by the user after the commodity link is clicked by the user in the same session.
In some embodiments, the value ranges of the target component, the global component, and the session component are the same.
In some embodiments, the historical order conversion rate includes a historical order quantity conversion rate and a historical order amount conversion rate, the resource configuration data is positively correlated with the historical order quantity conversion rate, and the resource configuration data is positively correlated with the historical order amount conversion rate.
In some embodiments, generating the resource configuration data of the commodity link according to the historical click times and the historical order conversion rate of the commodity link includes: generating resource configuration data of the target commodity link according to the historical click times and the historical order conversion rate of the target commodity link; the method for inputting the commodity identification and the resource configuration data of the commodity link into the link publishing engine comprises the following steps: inputting the target commodity identification and the resource configuration data linked with the target commodity into a link publishing engine; the historical order quantity conversion rate of the target commodity link is as follows: the product of the historical order number of the target commodity link and the historical click times of all the commodity links is divided by the product of the historical click times of the target commodity link and the historical order number of all the commodity links; the historical order limit conversion rate of the target commodity link is as follows: the product of the historical order amount of the target commodity link and the historical click times of all the commodity links is divided by the product of the historical click times of the target commodity link and the historical order amount of all the commodity links.
In some embodiments, generating the resource configuration data of the commodity link according to the historical click times and the historical order conversion rate of the commodity link further includes: and under the condition that the click times of the commodity link in the preset time period are greater than a third threshold value, adjusting the resource configuration data in real time according to the click times of the commodity link in the preset time period, wherein the resource configuration data after being adjusted in real time is in negative correlation with the click times of the commodity link in the preset time period.
According to another aspect of the embodiments of the present disclosure, there is provided a data processing apparatus including: a data generation module configured to: generating resource configuration data of the commodity link according to the historical click times and the historical order conversion rate of the commodity link; the resource configuration data is in negative correlation with the historical click times, and the resource configuration data is in positive correlation with the historical order conversion rate; a data input module configured to: and inputting the commodity identification and the resource configuration data of the commodity link into the link publishing engine so that the link publishing engine publishes the commodity link according to the commodity identification and the resource configuration data of the commodity link.
In some embodiments, the data generation module is configured to: generating a resource configuration data reference value of the commodity link according to the historical click times and the historical order conversion rate of the commodity link; determining a value interval of the resource configuration data of the commodity link according to the historical click times and the historical order conversion rate of the commodity link; and mapping the reference value of the resource configuration data to a value interval to obtain the resource configuration data.
In some embodiments, the data generation module is configured to: under the condition that the historical click times are larger than a first threshold value and the historical order conversion rate is larger than a second threshold value, the value-taking interval is [ F ]1,F2](ii) a Under the condition that the historical click times are not more than a first threshold value and the historical order conversion rate is more than a second threshold value, the value-taking interval is [ F ]1,F3](ii) a Under the condition that the historical click times are larger than a first threshold value and the historical order conversion rate is not larger than a second threshold value, the value-taking interval is [ F ]3,F5](ii) a Under the condition that the historical click times are larger than a first threshold value and the historical order conversion rate is not larger than a second threshold value, the value-taking interval is [ F ]4,F5](ii) a Wherein, F1>F2>F3>F4>F5>0。
In some embodiments, the data generation module is configured to: generating a target component of a resource configuration data reference value according to the historical click times and the historical order conversion rate of the commodity link in the target link publishing engine; generating a global component of a resource configuration data reference value according to historical click times and historical order conversion rates of commodity links in all link publishing engines; determining a resource configuration data reference value of the commodity link in the target link publishing engine according to the sum of the target component and the global component; determining a value interval of resource configuration data of the commodity link according to the historical click times and the historical order conversion rate of the commodity link in the target link publishing engine; mapping the resource configuration data reference value of the commodity link in the target link publishing engine to a value range to obtain the resource configuration data of the commodity link in the target link publishing engine; the data input module is configured to: and inputting the commodity identification and the resource configuration data of the commodity link in the target link publishing engine into the target link publishing engine.
In some embodiments, the data generation module is configured to: adding the target component, the global component and the session component to obtain a resource configuration data reference value of the commodity link in a target link publishing engine; the session components are: and the number of sessions that the commodity is added into a shopping cart or placed by the user after the commodity link is clicked by the user in the same session.
In some embodiments, the value ranges of the target component, the global component, and the session component are the same.
In some embodiments, the historical order conversion rate includes a historical order quantity conversion rate and a historical order amount conversion rate, the resource configuration data is positively correlated with the historical order quantity conversion rate, and the resource configuration data is positively correlated with the historical order amount conversion rate.
In some embodiments, the data generation module is configured to: generating resource configuration data of the target commodity link according to the historical click times and the historical order conversion rate of the target commodity link; the data input module is configured to: inputting the target commodity identification and the resource configuration data linked with the target commodity into a link publishing engine; the historical order quantity conversion rate of the target commodity link is as follows: the product of the historical order number of the target commodity link and the historical click times of all the commodity links is divided by the product of the historical click times of the target commodity link and the historical order number of all the commodity links; the historical order limit conversion rate of the target commodity link is as follows: the product of the historical order amount of the target commodity link and the historical click times of all the commodity links is divided by the product of the historical click times of the target commodity link and the historical order amount of all the commodity links.
In some embodiments, the data generation module is further configured to: and under the condition that the click times of the commodity link in the preset time period are greater than a third threshold value, adjusting the resource configuration data in real time according to the click times of the commodity link in the preset time period, wherein the resource configuration data after being adjusted in real time is in negative correlation with the click times of the commodity link in the preset time period.
According to still another aspect of the embodiments of the present disclosure, there is provided a data processing apparatus including: a memory; and a processor coupled to the memory, the processor configured to perform the aforementioned data processing method based on instructions stored in the memory.
According to still another aspect of the embodiments of the present disclosure, there is provided a computer-readable storage medium, wherein the computer-readable storage medium stores computer instructions, and the instructions, when executed by a processor, implement the aforementioned data processing method.
According to the method and the device, the resource configuration data input to the link publishing engine can be determined for a single commodity link according to the historical click times and the historical order conversion rate of the commodity link, so that the order conversion rate of the commodity link is improved, and the publishing efficiency of the commodity link is improved.
Other features of the present disclosure and advantages thereof will become apparent from the following detailed description of exemplary embodiments thereof, which proceeds with reference to the accompanying drawings.
Drawings
In order to more clearly illustrate the embodiments of the present disclosure or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below, it is obvious that the drawings in the following description are only some embodiments of the present disclosure, and for those skilled in the art, other drawings can be obtained according to the drawings without inventive exercise.
Fig. 1 shows a flow diagram of a data processing method of some embodiments of the present disclosure.
FIG. 2 illustrates a flow diagram of some embodiments of generating a merchandise link.
Fig. 3 shows a classification diagram of the goods link.
Fig. 4 shows a schematic structural diagram of a data processing apparatus according to some embodiments of the present disclosure.
Fig. 5 shows a schematic structural diagram of a data processing apparatus according to further embodiments of the present disclosure.
Detailed Description
The technical solutions in the embodiments of the present disclosure will be clearly and completely described below with reference to the drawings in the embodiments of the present disclosure, and it is obvious that the described embodiments are only a part of the embodiments of the present disclosure, and not all of the embodiments. The following description of at least one exemplary embodiment is merely illustrative in nature and is in no way intended to limit the disclosure, its application, or uses. All other embodiments, which can be derived by a person skilled in the art from the embodiments disclosed herein without making any creative effort, shall fall within the protection scope of the present disclosure.
The inventor researches and discovers that tens of thousands of commodities are usually contained in the same commodity group, the order conversion rates of the commodity links of the commodities are usually different, and the resource configuration is wasted by setting uniform resource configuration data for the commodity links. For example, different brands of electronic products have different user concerns, and setting up uniform advertising bidding data for different brands of electronic products wastes not only bids, but also the opportunity to obtain more user traffic. Therefore, setting the resource configuration data with the commodity group as the granularity may cause the unreasonable setting of the resource configuration data, thereby causing the order conversion rate of the commodity link to be reduced, and further causing the issue efficiency of the commodity link to be low.
Some e-commerce platforms input a commodity recommendation index to the link publishing engine, the commodity recommendation index is positively correlated with the historical order conversion rate of the commodity link, and the link publishing engine selects the finally published commodity link according to the commodity recommendation index. On one hand, the commodity recommendation indexes are sparse, and the commodity recommendation indexes are difficult to calculate for all commodities respectively; on the other hand, the algorithm of the link issuing engine is usually set to be strongly related to the historical click rate of the commodity link, so that the link issuing engine can greatly weaken the commodity recommendation index input by the e-commerce platform.
In view of this, the present disclosure provides a data processing method, which can determine resource configuration data input to a link publishing engine for a single commodity link based on a historical click number and a historical order conversion rate of the commodity link, so as to improve the order conversion rate of the commodity link and further improve the publishing efficiency of the commodity link.
Some embodiments of the disclosed data processing method are first described in conjunction with fig. 1.
Fig. 1 shows a flow diagram of a data processing method of some embodiments of the present disclosure. As shown in fig. 1, the present embodiment includes steps S101 to S102.
In step S101, resource allocation data of the product link is generated based on the historical click count and the historical order conversion rate of the product link.
The resource configuration data and the historical click times are in negative correlation, and the resource configuration data and the historical order conversion rate are in positive correlation. The historical order conversion rate may include a historical order quantity conversion rate and a historical order amount conversion rate, the resource configuration data is positively correlated with the historical order quantity conversion rate, and the resource configuration data is positively correlated with the historical order amount conversion rate.
In order to obtain the historical click times and the historical order conversion rate of the commodity link, an order following mechanism based on commodity identification can be adopted on the basis of abundant commodity order data. For example, the history number of times that the commodity link is clicked, and the history order-placing number of times or the history order-placing amount of money that the user placed an order after clicking the commodity link are acquired on the link publishing engine side. Dividing the historical order placing times by the clicked historical times of the commodity link to obtain the historical order quantity conversion rate; and dividing the historical order placing amount by the historical times of clicking the commodity link to obtain the historical order amount conversion rate. The historical order quantity conversion rate and the historical order amount conversion rate can be used as the historical order quantity conversion rate.
Then, the resource allocation data of the commodity link can be generated according to the historical click frequency of the commodity link, the historical order conversion rate and the reference resource allocation data of the commodity link. For example, the reference resource allocation data of the commodity link is multiplied by the historical order conversion rate, and then is divided by the historical click frequency, so that the resource allocation data can be obtained.
In some embodiments, the resource configuration data of the target commodity link may be generated according to the historical click times and the historical order conversion rate of the target commodity link. And then inputting the target commodity identification and the resource configuration data linked with the target commodity into a link publishing engine. The historical order quantity conversion rate of the target commodity link is as follows: the product of the historical order number of the target commodity link and the historical click times of all the commodity links is divided by the product of the historical click times of the target commodity link and the historical order number of all the commodity links; the historical order limit conversion rate of the target commodity link is as follows: the product of the historical order amount of the target commodity link and the historical click times of all the commodity links is divided by the product of the historical click times of the target commodity link and the historical order amount of all the commodity links. The processing has the effect that the calculation result can embody the relative order conversion capability of the target commodity, so that the resource configuration data of the target commodity is more accurately determined.
In step S102, the resource configuration data of the product identifier and the product link is input into the link publishing engine, so that the link publishing engine publishes the product link according to the product identifier and the resource configuration data of the product link.
Although the link publishing engine selects the finally published commodity link according to the preset algorithm, the resource configuration parameter corresponding to each commodity link is set based on the strength of the order conversion capability of the commodity link, so that the commodity link is provided with the resource configuration parameter adaptive to the order conversion capability of the commodity link no matter which commodity link is published by the link publishing engine.
According to the method and the device, the order conversion capacity of the commodity link can be measured by taking the historical click times and the historical order conversion rate of the commodity link as the basis, and the resource configuration data input to the link publishing engine is determined for a single commodity link, so that the finally published commodity link has high order conversion capacity, the order conversion rate of the commodity link is improved, and the publishing efficiency of the commodity link is improved.
How to generate the commodity-linked resource configuration data is further described below in conjunction with fig. 2.
FIG. 2 illustrates a flow diagram of some embodiments of generating a merchandise link. As shown in fig. 2, the present embodiment includes steps S2011 to S2013.
In step S2011, a resource allocation data reference value of the product link is generated according to the historical click frequency and the historical order conversion rate of the product link.
When the reference value of the resource configuration data of the commodity link is generated, some calculation methods mentioned in step S101 may be specifically adopted, which is not described herein again.
In step S2012, a value-taking interval of the resource allocation data of the commodity link is determined according to the historical click frequency and the historical order conversion rate of the commodity link.
The data condition of the commodity links is variable, the number of times that some commodity links are clicked is high, and the order conversion rate is low; the conversion rate of the partial commodity link order is high, but the clicked times are low. Therefore, the commodity links can be divided into four types according to the flow acquisition capacity and the order conversion capacity of the commodity links, and different resource configuration data adjustment strategies are formulated respectively.
Because the number of the commodities is huge, the commodities can be grouped before the value range of the resource configuration data linked with the commodities is determined. For example, commodities with similar orders placed by users or similar historical order conversion rates can be divided into a group. Then, the grouped commodities are classified to determine the value interval of the resource configuration data linked with the commodities.
Fig. 3 shows a classification diagram of the goods link. As shown in fig. 3, the horizontal axis represents the historical order conversion rate of the product link, the vertical axis represents the historical click frequency (abbreviated as flow rate) of the product link, the horizontal dotted line corresponds to the first threshold, and the vertical dotted line corresponds to the second threshold. The method can be used for dealing with different service requirements under different service scenes, and can divide commodity links into four types: the method comprises a flow type, a conversion type, a double-high type and a long tail type, thereby formulating different resource configuration data adjustment strategies. For example, when the historical click number is greater than a first threshold and the historical order conversion rate is greater than a second threshold, the value interval of the resource configuration data is [ F [ ]1,F2](ii) a Under the condition that the historical click times are not more than a first threshold value and the historical order conversion rate is more than a second threshold value, the value interval of the resource configuration data is [ F ]1,F3](ii) a Under the condition that the historical click times are larger than a first threshold value and the historical order conversion rate is not larger than a second threshold value, the value interval of the resource configuration data is [ F ]3,F5](ii) a Under the condition that the historical click times are larger than a first threshold value and the historical order conversion rate is not larger than a second threshold value, the value interval of the resource configuration data is [ F ]4,F5](ii) a Wherein, F1>F2>F3>F4>F5>0。
In step S2013, the resource allocation data reference value is mapped to the value-taking interval, so as to obtain resource allocation data.
In this embodiment, a reasonable value range is set for the commodity link according to the flow obtaining capability and the order conversion capability of the commodity link, so that the resource configuration data can be more accurately determined for the commodity link, and the order conversion rate and the release efficiency of the commodity link are further improved.
In some embodiments, the embodiment corresponding to fig. 2 further includes steps S2014 to S2015.
In step S2014, it is determined whether the click frequency of the commodity link within the preset time period is greater than a third threshold.
Returning to the step S2014 under the condition that the click times of the commodity link in the preset time period are not more than the third threshold value; in a case where the number of clicks of the article link is greater than the third threshold value within the preset period, step S2015 is performed.
In step S2015, the resource configuration data is adjusted in real time according to the click times of the commodity links in the preset time period, and the resource configuration data adjusted in real time is negatively related to the click times of the commodity links in the preset time period.
In consideration of the fact that the order conversion rate may be reduced after the flow of the commodity link is explosively increased, the embodiment can reduce the resource configuration data in real time after the flow of the commodity link is explosively increased, so that negative effects brought to the order conversion rate due to the explosively increased flow of the commodity link are avoided, and the order conversion rate and the release efficiency of the commodity link are further improved.
In some embodiments, when the resource configuration data of the commodity link is calculated by using the historical data, not only the historical data under the target link publishing engine may be used, but also the historical data under all other link publishing engines may be referred to (those skilled in the art may even set a weight ratio for the historical data under the target link publishing engine and the historical data under the other link publishing engines according to actual needs), so that the resource configuration data of the commodity link is calculated in all aspects.
For example, in step S2011, first, a target component of the resource allocation data reference value is generated according to the historical click frequency and the historical order conversion rate of the commodity link in the target link publishing engine; then, generating a global component of a resource configuration data reference value according to historical click times and historical order conversion rates of the commodity links in all link publishing engines; and finally, determining a resource configuration data reference value of the commodity link in the target link publishing engine according to the sum of the target component and the global component. Or adding the target component, the global component and the session component to obtain a resource configuration data reference value of the commodity link in the target link publishing engine; the session components are: and the number of sessions that the commodity is added into a shopping cart or placed by the user after the commodity link is clicked by the user in the same session. The value ranges of the target component, the global component and the session component may be the same.
Correspondingly, in step S2012, a value range of the resource configuration data of the commodity link is determined according to the historical click times and the historical order conversion rate of the commodity link in the target link publishing engine.
Correspondingly, in step S2013, the resource configuration data reference value of the commodity linked in the target link publishing engine is mapped to the value taking interval, and the resource configuration data of the commodity linked in the target link publishing engine is obtained, so that the commodity identification and the resource configuration data of the commodity linked in the target link publishing engine are input into the target link publishing engine.
Some specific calculation formulas are shown below to describe the data processing method in the present disclosure.
Let P denote the set of commodity links P for which resource allocation parameters need to be set, denoted as Pi(i ═ 0,1, … n) ∈ P; x represents a set of characteristics X of each product link, denoted as Xk(k＝click,gmv,ord…)∈X，pi(xclick) Indicating a product link piThe number of clicks of (1).
If W represents a set of W data, equation (1) is used:
w can be mapped to an interval [0,2], and S (w, C) belongs to [0,2], wherein C represents a constant; minW and maxW represent the minimum and maximum values, respectively, of a set of data W.
Using equation (2):
w may be mapped to an interval [ C ]min,Cmax]Guarantee N (w, C)min,Cmax)∈[Cmin,Cmax]Where minW and maxW represent the minimum and maximum values, respectively, of a set of data W.
Using equation (3):
the product link characteristic p (x) can be calculatedb) Linking feature p (x) with merchandisea) Preventing the occurrence of p (x) in the relative ratio ofb)/p(xa) Problem of too large data range, let p (x)b)/p(xa) The data credibility is higher.
Then, according to equations (1), (2), (3), equation (4) can be employed:
to calculate a resource allocation data reference value R (p) of the commodity link; wherein C represents a constant and is generally 1; alpha and beta are preset service parameters; p (x)click) Representing the historical click times of each commodity link on the target link publishing engine; p (x)gmv) Showing the historical order conversion limit of each commodity link at the target link publishing engine; p (x)ord) Representing the historical order conversion quantity of each commodity in the target link publishing engine; p (x)r_click) Representing the historical click times of each commodity in other link publishing engines; p (x)r_gmv) Showing the historical order conversion limit of each commodity in other linked publishing engines; p (x)r_ord) Representing the historical order conversion quantity of each commodity in other linked publishing engines; p (x)cvt_session) The commodity link is clicked by the user, and the conversation times of commodities corresponding to the purchase adding and order placing are simultaneously in the same conversation; b (p) represents reference resource allocation data.
Next, determining a value interval of the resource configuration data of the commodity link, mapping the reference value of the resource configuration data to the value interval, and obtaining the resource configuration data, namely, formula (5):
wherein QAIndicating the flow type, QBRepresenting a double high type, QcDenotes the long tail form, QDRepresents a transformation type;
respectively take the boundary value of the interval to satisfy
Finally, adjusting the resource configuration data according to the real-time traffic, namely, formula (6):
wherein Ratioreal(p) resource allocation data adjusted in real time, p (x)real_click) Indicating the historical number of clicks of the item link on the last day,
d. e, f are traffic parameters.
The above equations (1) - (7) are only used as examples and not as specific limitations, and those skilled in the art can also use similar or similar means to determine the relevant calculation equations. Meanwhile, those skilled in the art should understand that if detailed user tags can be obtained, users can be precisely oriented, dimension data of user matching degree can be increased, and resource configuration parameters can be adjusted for a single user.
Some embodiments of the disclosed data processing apparatus are described below in conjunction with fig. 4.
Fig. 4 shows a schematic structural diagram of a data processing apparatus according to some embodiments of the present disclosure. As shown in fig. 4, the data processing apparatus 40 in the present embodiment includes: a data generation module 401 configured to: generating resource configuration data of the commodity link according to the historical click times and the historical order conversion rate of the commodity link; the resource configuration data is in negative correlation with the historical click times, and the resource configuration data is in positive correlation with the historical order conversion rate; a data input module 402 configured to: and inputting the commodity identification and the resource configuration data of the commodity link into the link publishing engine so that the link publishing engine publishes the commodity link according to the commodity identification and the resource configuration data of the commodity link.
According to the method and the device, the order conversion capacity of the commodity link can be measured by taking the historical click times and the historical order conversion rate of the commodity link as the basis, and the resource configuration data input to the link publishing engine is determined for a single commodity link, so that the finally published commodity link has high order conversion capacity, the order conversion rate of the commodity link is improved, and the publishing efficiency of the commodity link is improved.
In some embodiments, the data generation module 401 is configured to: generating a resource configuration data reference value of the commodity link according to the historical click times and the historical order conversion rate of the commodity link; determining a value interval of the resource configuration data of the commodity link according to the historical click times and the historical order conversion rate of the commodity link; and mapping the reference value of the resource configuration data to a value interval to obtain the resource configuration data.
In some embodiments, the data generation module 401 is configured to: under the condition that the historical click times are larger than a first threshold value and the historical order conversion rate is larger than a second threshold value, the value-taking interval is [ F ]1,F2](ii) a Under the condition that the historical click times are not more than a first threshold value and the historical order conversion rate is more than a second threshold value, the value-taking interval is [ F ]1,F4](ii) a Under the condition that the historical click times are larger than a first threshold value and the historical order conversion rate is not larger than a second threshold value, the value-taking interval is [ F ]4,F5](ii) a Under the condition that the historical click times are larger than a first threshold value and the historical order conversion rate is not larger than a second threshold value, the value-taking interval is [ F ]4,F5](ii) a Wherein, F1>F2>F4>F4>F5>0。
In this embodiment, a reasonable value range is set for the commodity link according to the flow obtaining capability and the order conversion capability of the commodity link, so that the resource configuration data can be more accurately determined for the commodity link, and the order conversion rate and the release efficiency of the commodity link are further improved.
In some embodiments, the data generation module 401 is configured to: generating a target component of a resource configuration data reference value according to the historical click times and the historical order conversion rate of the commodity link in the target link publishing engine; generating a global component of a resource configuration data reference value according to historical click times and historical order conversion rates of commodity links in all link publishing engines; determining a resource configuration data reference value of the commodity link in the target link publishing engine according to the sum of the target component and the global component; determining a value interval of resource configuration data of the commodity link according to the historical click times and the historical order conversion rate of the commodity link in the target link publishing engine; mapping the resource configuration data reference value of the commodity link in the target link publishing engine to a value range to obtain the resource configuration data of the commodity link in the target link publishing engine; the data input module is configured to: and inputting the commodity identification and the resource configuration data of the commodity link in the target link publishing engine into the target link publishing engine.
In some embodiments, the data generation module 401 is configured to: adding the target component, the global component and the session component to obtain a resource configuration data reference value of the commodity link in a target link publishing engine; the session components are: and the number of sessions that the commodity is added into a shopping cart or placed by the user after the commodity link is clicked by the user in the same session.
In some embodiments, the value ranges of the target component, the global component, and the session component are the same.
In some embodiments, the historical order conversion rate includes a historical order quantity conversion rate and a historical order amount conversion rate, the resource configuration data is positively correlated with the historical order quantity conversion rate, and the resource configuration data is positively correlated with the historical order amount conversion rate.
In some embodiments, the data generation module 401 is configured to: generating resource configuration data of the target commodity link according to the historical click times and the historical order conversion rate of the target commodity link; the data input module is configured to: inputting the target commodity identification and the resource configuration data linked with the target commodity into a link publishing engine; the historical order quantity conversion rate of the target commodity link is as follows: the product of the historical order number of the target commodity link and the historical click times of all the commodity links is divided by the product of the historical click times of the target commodity link and the historical order number of all the commodity links; the historical order limit conversion rate of the target commodity link is as follows: the product of the historical order amount of the target commodity link and the historical click times of all the commodity links is divided by the product of the historical click times of the target commodity link and the historical order amount of all the commodity links.
In some embodiments, the data generation module 401 is further configured to: and under the condition that the click times of the commodity link in the preset time period are greater than a third threshold value, adjusting the resource configuration data in real time according to the click times of the commodity link in the preset time period, wherein the resource configuration data after being adjusted in real time is in negative correlation with the click times of the commodity link in the preset time period.
In consideration of the fact that the order conversion rate may be reduced after the flow of the commodity link is explosively increased, the embodiment can reduce the resource configuration data in real time after the flow of the commodity link is explosively increased, so that negative effects brought to the order conversion rate due to the explosively increased flow of the commodity link are avoided, and the order conversion rate and the release efficiency of the commodity link are further improved.
Further embodiments of the data processing apparatus of the present disclosure are described below in conjunction with fig. 5.
Fig. 5 shows a schematic structural diagram of a data processing apparatus according to further embodiments of the present disclosure. As shown in fig. 5, the data processing apparatus 50 of this embodiment includes: a memory 510 and a processor 520 coupled to the memory 510, the processor 520 being configured to perform the data processing method of any of the foregoing embodiments based on instructions stored in the memory 510.
The data processing apparatus 50 may further include an input-output interface 530, a network interface 540, a storage interface 550, and the like. These interfaces 530, 540, 550 and the connections between the memory 510 and the processor 520 may be, for example, via a bus 560. The input/output interface 530 provides a connection interface for input/output devices such as a display, a mouse, a keyboard, and a touch screen. The network interface 540 provides a connection interface for various networking devices. The storage interface 550 provides a connection interface for external storage devices such as an SD card and a usb disk.
The present disclosure also includes a computer readable storage medium having stored thereon computer instructions which, when executed by a processor, implement a data processing method in any of the foregoing embodiments.
The present disclosure is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the disclosure. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The above description is only exemplary of the present disclosure and is not intended to limit the present disclosure, so that any modification, equivalent replacement, or improvement made within the spirit and principle of the present disclosure should be included in the scope of the present disclosure.
Claims (12)
1. A method of data processing, comprising:
generating resource configuration data of the commodity link according to the historical click times and the historical order conversion rate of the commodity link; the resource configuration data is in negative correlation with the historical click times, and the resource configuration data is in positive correlation with the historical order conversion rate;
and inputting the commodity identification and the resource configuration data of the commodity link into the link publishing engine so that the link publishing engine publishes the commodity link according to the commodity identification and the resource configuration data of the commodity link.
2. The data processing method of claim 1, wherein the generating resource configuration data of the commodity link according to the historical click times and the historical order conversion rate of the commodity link comprises:
generating a resource configuration data reference value of the commodity link according to the historical click times and the historical order conversion rate of the commodity link;
determining a value interval of the resource configuration data of the commodity link according to the historical click times and the historical order conversion rate of the commodity link;
and mapping the reference value of the resource configuration data to the value interval to obtain the resource configuration data.
3. The data processing method of claim 2, wherein the determining a value interval of the resource configuration data of the commodity link according to the historical click times and the historical order conversion rate of the commodity link comprises:
under the condition that the historical click times are greater than a first threshold value and the historical order conversion rate is greater than a second threshold value, the value-taking interval is [ F1,F2]；
Under the condition that the historical click times are not more than a first threshold value and the historical order conversion rate is more than a second threshold value, the value-taking interval is [ F1,F3]；
Under the condition that the historical click times are larger than a first threshold value and the historical order conversion rate is not larger than a second threshold value, the value-taking interval is [ F3,F5]；
Under the condition that the historical click times are larger than a first threshold value and the historical order conversion rate is not larger than a second threshold value, the value-taking interval is [ F4,F5]；
Wherein, F1>F2>F3>F4>F5>0。
4. The data processing method according to claim 2,
the generating of the resource configuration data reference value of the commodity link according to the historical click times and the historical order conversion rate of the commodity link comprises: generating a target component of the resource configuration data reference value according to the historical click times and the historical order conversion rate of the commodity link in the target link publishing engine; generating a global component of the resource configuration data reference value according to historical click times and historical order conversion rates of commodity links in all link publishing engines; determining a resource configuration data reference value of the commodity link in a target link publishing engine according to the sum of the target component and the global component;
the determining the value interval of the resource configuration data of the commodity link according to the historical click times and the historical order conversion rate of the commodity link comprises the following steps: determining a value interval of resource configuration data of the commodity link according to the historical click times and the historical order conversion rate of the commodity link in the target link publishing engine;
mapping the resource configuration data reference value to the value interval, and obtaining the resource configuration data includes: mapping the resource configuration data reference value of the commodity link in the target link publishing engine to the value taking interval to obtain the resource configuration data of the commodity link in the target link publishing engine;
the input link publishing engine for the commodity identification and the resource configuration data linked with the commodity comprises: and inputting the commodity identification and the resource configuration data of the commodity link in the target link publishing engine into the target link publishing engine.
5. The data processing method of claim 4, wherein the determining a resource configuration data reference value of the commodity link in the target link publishing engine according to the sum of the target component and the global component comprises:
adding the target component, the global component and the session component to obtain a resource configuration data reference value of the commodity link in a target link publishing engine; the session component is: and the number of sessions that the commodity is added into a shopping cart or placed by the user after the commodity link is clicked by the user in the same session.
6. The data processing method of claim 5, wherein the target component, the global component, and the session component have the same value range.
7. The data processing method of claim 1, wherein the historical order conversion rate comprises a historical order quantity conversion rate and a historical order amount conversion rate, the resource configuration data is positively correlated with the historical order quantity conversion rate, and the resource configuration data is positively correlated with the historical order amount conversion rate.
8. The data processing method of claim 7,
the generating of the resource configuration data of the commodity link according to the historical click times and the historical order conversion rate of the commodity link comprises: generating resource configuration data of the target commodity link according to the historical click times and the historical order conversion rate of the target commodity link;
the input link publishing engine for the commodity identification and the resource configuration data linked with the commodity comprises: inputting the target commodity identification and the resource configuration data linked with the target commodity into a link publishing engine;
the historical order quantity conversion rate of the target commodity link is as follows: the product of the historical order number of the target commodity link and the historical click times of all the commodity links is divided by the product of the historical click times of the target commodity link and the historical order number of all the commodity links; the historical order limit conversion rate of the target commodity link is as follows: the product of the historical order amount of the target commodity link and the historical click times of all the commodity links is divided by the product of the historical click times of the target commodity link and the historical order amount of all the commodity links.
9. The data processing method of claim 2, wherein the generating resource configuration data of the commodity link according to the historical click times and the historical order conversion rate of the commodity link further comprises:
and under the condition that the click times of the commodity link in the preset time period are greater than a third threshold value, adjusting the resource configuration data in real time according to the click times of the commodity link in the preset time period, wherein the resource configuration data after being adjusted in real time is in negative correlation with the click times of the commodity link in the preset time period.
10. A data processing apparatus comprising:
a data generation module configured to: generating resource configuration data of the commodity link according to the historical click times and the historical order conversion rate of the commodity link; the resource configuration data is in negative correlation with the historical click times, and the resource configuration data is in positive correlation with the historical order conversion rate;
a data input module configured to: and inputting the commodity identification and the resource configuration data of the commodity link into the link publishing engine so that the link publishing engine publishes the commodity link according to the commodity identification and the resource configuration data of the commodity link.
11. A data processing apparatus comprising:
a memory; and
a processor coupled to the memory, the processor configured to perform the data processing method of any of claims 1 to 10 based on instructions stored in the memory.
12. A computer-readable storage medium, wherein the computer-readable storage medium stores computer instructions which, when executed by a processor, implement a data processing method as claimed in any one of claims 1 to 10.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010228286.4A CN113450168A (en) | 2020-03-27 | 2020-03-27 | Data processing method, device and computer readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010228286.4A CN113450168A (en) | 2020-03-27 | 2020-03-27 | Data processing method, device and computer readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113450168A true CN113450168A (en) | 2021-09-28 |
Family
ID=77807881
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010228286.4A Pending CN113450168A (en) | 2020-03-27 | 2020-03-27 | Data processing method, device and computer readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113450168A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107346505A (en) * | 2016-05-06 | 2017-11-14 | 北京京东尚科信息技术有限公司 | Information-pushing method and device |
| CN107895299A (en) * | 2017-11-08 | 2018-04-10 | 浙江执御信息技术有限公司 | The exposure sort method and device of a kind of commodity |
| US20190362408A1 (en) * | 2018-05-25 | 2019-11-28 | Target Brands, Inc. | Personalized recommendations for unidentified users based on web browsing context |
| CN110750717A (en) * | 2019-09-27 | 2020-02-04 | 上海麦克风文化传媒有限公司 | Sorting weight updating method |
| CN110852818A (en) * | 2018-08-20 | 2020-02-28 | 北京京东尚科信息技术有限公司 | Commodity sorting method and device and computer-readable storage medium |
-
2020
- 2020-03-27 CN CN202010228286.4A patent/CN113450168A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107346505A (en) * | 2016-05-06 | 2017-11-14 | 北京京东尚科信息技术有限公司 | Information-pushing method and device |
| CN107895299A (en) * | 2017-11-08 | 2018-04-10 | 浙江执御信息技术有限公司 | The exposure sort method and device of a kind of commodity |
| US20190362408A1 (en) * | 2018-05-25 | 2019-11-28 | Target Brands, Inc. | Personalized recommendations for unidentified users based on web browsing context |
| CN110852818A (en) * | 2018-08-20 | 2020-02-28 | 北京京东尚科信息技术有限公司 | Commodity sorting method and device and computer-readable storage medium |
| CN110750717A (en) * | 2019-09-27 | 2020-02-04 | 上海麦克风文化传媒有限公司 | Sorting weight updating method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102346894B (en) | The output intent of recommendation information, system and server | |
| JP2011138470A (en) | Patent evaluation method, and computer-readable storage medium therefor | |
| CN105808347B (en) | Cluster server disposes computational methods and device | |
| KR102574244B1 (en) | A method and apparatus for generating future demand forecast data based on attention mechanism | |
| CN112506657B (en) | Resource management system facing micro service based on reinforcement learning | |
| CN108573348A (en) | Financial indicator distributed computing method and its system | |
| CN107688901B (en) | Data adjusting method and device | |
| CN114049162B (en) | Model training method, demand prediction method, apparatus, device, and storage medium | |
| CN116911962A (en) | Article selecting device and method based on data model | |
| US20120185326A1 (en) | Contact stream optimization using fec and cc constraints | |
| CN116562992A (en) | Method, device and medium for recommending items for modeling uncertainty of new interests of user | |
| CN111967927A (en) | Commercial purchasing method for calculating satisfaction degree through multiple criteria | |
| CN108932241A (en) | Daily record data statistical method, device and node | |
| CN113450168A (en) | Data processing method, device and computer readable storage medium | |
| CN110599281A (en) | Method and device for determining target shop | |
| EP3573003A1 (en) | Systems and methods for estimating validation time for fraud detection rules | |
| CN114298319B (en) | Determination method and device for joint learning contribution value, electronic equipment and storage medium | |
| CN111626758A (en) | Online marketing management method based on big data | |
| Rostoker et al. | A parallel workflow for real-time correlation and clustering of high-frequency stock market data | |
| CN111984637B (en) | Missing value processing method and device in data modeling, equipment and storage medium | |
| CN113344208A (en) | Data reasoning method, device and system | |
| CN114463065A (en) | Pricing method, pricing device, computer equipment and storage medium | |
| CN109934604B (en) | Sales data processing method and system, storage medium and electronic equipment | |
| CN113379533A (en) | Method, device, equipment and storage medium for improving circulating loan quota | |
| CN110544129A (en) | Personalized recommendation method for social e-commerce users |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |